Run 4. Outer Step 26. Inner Step 39.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535830,
-    5535833,
-    5535835,
-    5535838,
-    5535841,
-    5535844,
-    5535846,
-    5535849
+    5535852,
+    5535853,
+    5535855,
+    5535857,
+    5535859
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b68a82fba374eb67e8aeb266c5de88cfe1e7d0872582c78e95c13d582311e8
+oid sha256:e21048d1877733500b4eef6d750ffdbf041e411db7754cb88ff9de16f7b03f1a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca9a39f3a82f6e9445559525cbe36b5ba11507fe8c23f44d0526babc342ab20
+oid sha256:16a99646292ac0e38a7be91e0d63cd8580c8c66ed70a30a2a3bdc137f7c0a210
 size 4040701744